Create app.py

app.py

@@ -0,0 +1,44 @@
+import torch
+from diffusers import UniPCMultistepScheduler
+from diffusers import WanPipeline, AutoencoderKLWan  # Use Wan-specific VAE
+from diffusers.models import UNetSpatioTemporalConditionModel
+from transformers import T5EncoderModel, T5Tokenizer
+
+from PIL import Image
+import numpy as np
+
+model_id = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"
+vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
+flow_shift = 5.0  # 5.0 for 720P, 3.0 for 480P
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=flow_shift)
+pipe.to("cuda")
+
+@spaces.GPU()
+def generate(prompt):
+    output = pipe(
+        prompt=prompt,
+        # negative_prompt=negative_prompt,
+        height=720,
+        width=1280,
+        num_frames=1,
+        num_inference_steps=28,
+        guidance_scale=5.0,
+    )
+    image = output.frames[0][0]
+    image = (image * 255).astype(np.uint8)
+    return Image.fromarray(image)
+
+iface = gr.Interface(
+    fn=generate,
+    inputs=[
+        gr.Textbox(label="Input prompt"),
+        # gr.Slider(label="Width", minimum=256, maximum=2048, step=8, value=1024),
+        # gr.Slider(label="Height", minimum=256, maximum=2048, step=8, value=1024),
+        # gr.Textbox(label="Lora ID", placeholder="Optional"),
+        # gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="Lora Scale", value=1)
+    ],
+    outputs=gr.Image(label="output"),
+)
+
+iface.launch()